Skip to content
MelMel
Reference > Settings & account

AI settings

Agent behavior: autodetection, thinking display, and voice.

The AI page (labeled Mel Agent in the content pane) configures how the agent behaves in conversations — input handling, the thinking stream, voice, and which model new conversations start on. Changes apply immediately and persist to ~/.mel/settings.json.

Input

  • Autodetect terminal commands in agent input (on by default) — when you type something that looks like a shell command into an agent conversation, Mel runs it as a command inside the conversation instead of sending it to the model. Press ctrl+I to override the detection for the current input, or prefix with ! to force a shell command. Turn this off if you want everything you type treated as a prompt.
  • Show input hint text (on by default) — controls the ghost autocomplete and the hint rows rendered under inputs.
  • AI command suggestions (on by default) — when your local autocomplete (session history, shell history, filesystem) has nothing to offer, Mel makes one lightweight backend call after a short typing pause and shows the suggested next command as ghost text. Disable this if you want autocomplete to stay fully local.

Thinking

  • Auto-open thoughts while streaming (on by default) — for models that emit reasoning, the collapsible Thoughts section expands automatically while the agent is thinking and collapses again when the response is done. With this off, Thoughts stays collapsed until you open it.

Voice

  • Voice input (on by default) — shows the mic in the tool belt and enables the local transcription hook. Note that transcription itself is a pluggable local hook today: Mel runs whatever command you set in the $MEL_VOICE_CMD environment variable; there is no cloud speech-to-text.

Default models

Two dropdowns, each offering auto plus every model in the catalog:

  • Base — new plain agent conversations start on this model.
  • Full terminal use — the default for orchestrator and autonomous conversations, where the agent drives the terminal itself.

Both default to auto, which routes each task to a suitable model instantly. Tip: ctrl+shift+click a model in the in-conversation model picker to select it *and* save it as your default here in one step.

Related